Ask HN: Current choice of AI code editor? | Hacker News Reader

Ask HN: Current choice of AI code editor?

4 pointschironjit10 comments

Hey all, I'm looking to move away from Cursor and curious what your choice of editor is? There are quite a few that I am only just hearing of now.

View on HN

Adding my review of the ones I have tried:

Cursor: I've been using Cursor and had to reinstall recently. Almost accidentally agreed to data sharing, which now is a compulsory must to agree on to use (or must be manually disabled later). Almost missed it, as I'm happy to share usage but not my code (A lot of the code I write have bits I would like to remain private, and anything I'm happy to make public is already public). Not super happy with this.

Their agent mode is also not that great, it either overshoots or misses because it doesn't get the context. Worse, it will refactor and delete other parts, such as comments that I put there as guides for myself.

Was happy to use it in chat though - really sped up my troubleshooting, and that itself made it worth the price. Also, the latest models are actually quite a lot better than the older one, especially for novel code.

Copilot (on VS Code): Stopped using it after I found cursor. The earlier autocomplete models were nice for boilerplate but now that I have used the newer models (deepseek, gemini 2.5 models, sonnet 4) those feel really bad, and not useful for novel code.

I couldn't find a way to turn off data sharing. Looks like they are forcing users to share data? I uninstalled since I don't want my code to end up on their servers.

IIRC you could select not to share your code previously when setting up, and while they would have used your code to provide you your service, that was it.

My understanding with the new wording is that you have to agree upfront to share your code, and turn it off later if you do not wish to share it.

I cpuldn’t find a way to turn off data sharing after being forced to agree to continue installation. So I uninstalled it.

Good bye Cursor

I use Copilot auto-complete in JetBrains IDEs and vscode. I use IDE at same time as terminals running Claude Code which I’ve found very helpful with simple stuff like “add command line flags that do these things” and “refactor this function to be in this other package instead”. I highly recommmend Claude Code as it works across all languages regardless of your preferred IDE.

Thanks, I'll check out Claude code. Their Sonnet model is one of the best honestly. Only issue is their context size is small when I have to dig in to some obscure error in a package

Continue (continue.dev) is worth checking out - it's open source, works as a VS Code extension, and lets you use your own local models or connect to various APIs while keeping your code private.

Cool, thank you, might check this out. Have you used it? Opinions on it?

Why did you decide to move away from Cursor?

Just posted my reply on the thread, to summarise:

1) Default sharing of code (only manual turn off)

2) Was an incident where I believe at least some versions would share your env files (without manual .cursorignore)

3) Agent mode is quiet bad for novel code

4) Agent mode either overshoots(overcomplicates code), mistakes context or refactors too much

The only benefit I get is:

a) Chatting in same window as my code

b) Ctrl+L shortcut

(edited for formatting)

Reply on news.ycombinator.com